us_renew <- read_csv(here::here("data", "renewables_cons_prod.csv")) %>%
clean_names()
renew_clean <- us_renew %>%
mutate(description = str_to_lower(description)) %>%
filter(str_detect(description, pattern = "consumption")) %>%
filter(!str_detect(description, pattern = "total"))
renew_date <-renew_clean %>%
mutate(yr_mo_day = lubridate::parse_date_time(yyyymm, "ym")) %>%
mutate(month_sep = yearmonth(yr_mo_day)) %>% # just pull out year and month, class will be yearmonth and date
mutate(value = as.numeric(value)) %>%
drop_na(month_sep, value) # specify the column, otherwise any rows have a na will be deleted
# make a version wher I have the month & year in separate columns
renew_parsed <- renew_date %>%
mutate(month = month(yr_mo_day, label = TRUE)) %>% # label --> write in text not numbers
mutate(year = year(yr_mo_day))
renew_gg <- ggplot(data = renew_date, aes(x = month_sep, y = value))+ # or aes(group = description)
geom_line(aes(color = description))+
theme_minimal()
renew_gg
updating colors with paletteer palettes:
renew_gg +
scale_color_paletteer_d("basetheme::brutal") # package_name::palette name
renew_ts <- as_tsibble(renew_parsed, key = description, index = month_sep) # index, the time column
let’s look at our ts data in a couple different ways:
renew_ts %>% autoplot(value)
renew_ts %>% gg_subseries(value)
renew_ts %>% gg_season(value)
# make the season plot in ggplot
ggplot(data = renew_parsed, aes(x = month, y = value, group = year))+
geom_line(aes(color = year))+
facet_wrap(~description,
ncol = 1,
scales = "free",
strip.position = "right") # great! change the facet proporties!
hydro_ts <- renew_ts %>%
filter(description == "hydroelectric power consumption")
hydro_ts %>% autoplot(value)
hydro_ts %>% gg_subseries(value)
hydro_ts %>% gg_season(value)
hydro_quarterly <- hydro_ts %>%
index_by(year_qu = ~(yearquarter(.))) %>% # great way to group, new_column = ~
summarize(avg_consumption = mean(value))
head(hydro_quarterly)
## # A tsibble: 6 x 2 [1Q]
## year_qu avg_consumption
## <qtr> <dbl>
## 1 1973 Q1 261.
## 2 1973 Q2 255.
## 3 1973 Q3 212.
## 4 1973 Q4 225.
## 5 1974 Q1 292.
## 6 1974 Q2 290.
dcmp <- hydro_ts %>%
model(STL(value ~ season(window = 5)))
components(dcmp) %>% autoplot()
hist(components(dcmp)$remainder)
Now lookat the ACF
hydro_ts %>%
feasts::ACF(value) %>%
autoplot()
# 12 months later have the most correlation
hydro_model <- hydro_ts %>%
model(
ARIMA(value),
ETS(value)
) %>%
fabletools::forecast(h = "4 years")
hydro_model %>% autoplot(filter(hydro_ts, year(month_sep) > 2010)) + theme_minimal()
world <- read_sf(dsn = here::here("data", "TM_WORLD_BORDERS_SIMPL-0.3-1"),
layer = "TM_WORLD_BORDERS_SIMPL-0.3")
mapview(world)